|
|||||
|
|
| 基于随机森林的长期目标跟踪方法 | |
| 引用本文： | 张丹,陈兴文,赵姝颖,程立英.基于随机森林的长期目标跟踪方法[J].大连民族学院学报,2015,17(3):259-264. |
| 作者姓名： | 张丹 陈兴文 赵姝颖 程立英 |
| 作者单位： | 1.大连民族学院 创新教育中心,辽宁 大连 116605; 2.东北大学 信息科学与工程学院,辽宁 沈阳 110819; 3.沈阳师范大学 物理科学与技术学院,辽宁 沈阳 110034 |
| 基金项目： | 中央高校基本科研业务费专项资金资助项目(DC201402060303)。 |
| 摘 要： | 结合正负样本相互作用思想和随机森林算法构建检测器,融合基于LK光流法的跟踪器,提出一种基于TLD(Tracking Learning Detecting)的随机森林长期目标跟踪方法。将该方法与Mean-Shift算法、TLD算法进行对比,结果表明该算法能很好应对目标丢失、遮挡情况,准确率在93%以上。在多种情况下对该方法进行实验验证,可实现刚性物体和非刚性物体在复杂背景下的长时间精确跟踪。 |
| 关 键 词： | TLD算法 随机森林 目标跟踪 LK光流法 |
Long-term Target Tracking Method Based on Random Forests |
|
| ZHANG Dan,CHEN Xing-wen,ZHAO Shu-ying,CHENG Li-ying.Long-term Target Tracking Method Based on Random Forests[J].Journal of Dalian Nationalities University,2015,17(3):259-264. | |
| Authors: | ZHANG Dan CHEN Xing-wen ZHAO Shu-ying CHENG Li-ying |
| Institution: | 1.Innovation Education Center, Dalian Nationalities University, Dalian Liaoning 116605, China; 2.College of Information Science and Engineering, Northeastern University, Shenyang Liaoning 110819, China; 3. College of Physics Science and Technology, Shenyang Normal University, Shenyang Liaoning 110034, China |
| Abstract: | In this paper, we propose a target tracking method based on Tracking Learning Detecting (TLD) random fores by using the detector constructed by the ideas of the interaction between positive and negative samples and random forest algorithm, and tracker based on LK optical flow method. This method is performed the comparison with the Mean Shift algorithm and TLD method. The results show that the algorithm can have the strong robustness to target lost, target occlusion, and the accuracy rate is more than 93%. The experiment results in many cases verify that this method can achieve a long time accurate tracking for rigid and non-rigid object in complex background. |
| Keywords: | TLD algorithm random forest target tracking LK optical flow method |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《大连民族学院学报》浏览原始摘要信息 | |
| 点击此处可从《大连民族学院学报》下载免费的PDF全文 | |